Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered. This paper is a pilot framework, not a benchmark claim. We formalize LLM-mediated decompression, define a protected/lossy packet architecture, and evaluate six representation regimes over five author-constructed diagnostic cases: structured prose, JSON, CCL-Core, CCL-Min, SemanticZip ASCII, and SemanticZip emoji. An independent decoder LLM reconstructs typed semantic atoms from each compressed representation, and we score Critical Atom Recall, Weighted Atom Recall, precision, and tokenizer gain. In this pilot, structured prose has the highest recoverability, with WAR = 0.956 and 19.1% o200k_base token gain. CCL-Min is the strongest balanced point, with 39.4% token gain and WAR = 0.874. SemanticZip ASCII provides the largest useful compression, with 46.5% token gain and WAR = 0.802, while emoji-heavy SemanticZip performs worse on both compression and recovery. The main contribution is not the claim that these numbers establish a universal frontier. Rather, we introduce a reproducible experimental interface for studying lossy, LLM-decompressible text codes and a design principle: safety-critical and exact commitments should remain protected, while predictable low-risk context may be semantically zipped.

翻译：针对大语言模型系统的文本压缩通常被界定为token删除、检索、摘要或精确重建。本研究探索一种更为激进但明确有损的设定：将文本压缩为紧凑编码，使LLM能够将其扩展为与任务相关的语义。我们将此设定命名为SemanticZip。与无损压缩不同，SemanticZip不要求字节级精确重建；与常规摘要不同，它将基于模型的解压缩视为编解码器的一部分，并评估任务相关语义承诺是否被恢复。本文是探索性框架而非基准声明。我们形式化了LLM介导的解压缩过程，定义了受保护/有损数据包架构，并在五个作者构建的诊断案例中评估了六种表征模式：结构化散文、JSON、CCL-Core、CCL-Min、SemanticZip ASCII和SemanticZip表情符。独立的解码器LLM从每种压缩表征中重建带类型语义原子，我们评估关键原子召回率，加权原子召回率、精确率和token压缩率。在本探索性研究中，结构化散文具有最高的可恢复性，WAR=0.956，o200k_base token压缩率达19.1%；CCL-Min是最优平衡点，token压缩率39.4%，WAR=0.874；SemanticZip ASCII提供最大的有效压缩，token压缩率46.5%，WAR=0.802；而表情符密集的SemanticZip在压缩和恢复方面均表现较差。主要贡献并非宣称这些数字确立了通用最优边界，而是引入了一个可复现的实验接口用于研究有损、LLM可解压缩的文本编码，以及一个设计原则：安全关键和精确承诺应保持受保护，而可预测的低风险上下文可进行语义压缩。